diff --git "a/tokenizer.json" "b/tokenizer.json" new file mode 100644--- /dev/null +++ "b/tokenizer.json" @@ -0,0 +1,500929 @@ +{ + "version": "1.0", + "truncation": null, + "padding": null, + "added_tokens": [ + { + "id": 0, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 1, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 2, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 3, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 4, + "content": "<|system|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 5, + "content": "<|user|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 6, + "content": "<|assistant|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 7, + "content": "<|end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 8, + "content": "<|reserved_special_token_0|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 9, + "content": "<|reserved_special_token_1|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 10, + "content": "<|reserved_special_token_2|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 11, + "content": "<|reserved_special_token_3|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 12, + "content": "<|reserved_special_token_4|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 13, + "content": "<|reserved_special_token_5|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 14, + "content": "<|reserved_special_token_6|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 15, + "content": "<|reserved_special_token_7|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 16, + "content": "<|reserved_special_token_8|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 17, + "content": "<|reserved_special_token_9|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 18, + "content": "<|reserved_special_token_10|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 19, + "content": "<|reserved_special_token_11|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 20, + "content": "<|reserved_special_token_12|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 21, + "content": "<|reserved_special_token_13|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 22, + "content": "<|reserved_special_token_14|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 23, + "content": "<|reserved_special_token_15|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 100352, + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + { + "id": 100353, + "content": "